Document to Markdown for AI Agents

Give it the URLs of PDF, Word (DOCX), PowerPoint (PPTX) or Excel (XLSX) files and get each one back as clean markdown, for AI agents and RAG pipelines that need the text of a document, not a file. You get one dataset item per document.

• Reads public URLs only, and respects robots.txt for every document and every redirect. It identifies itself as FrameskimFetch.
• Word and PowerPoint files keep headings, lists and tables as markdown; Excel sheets become tables.
• PDFs come back as plain text, page by page, without tables. A PDF's title is the one in its metadata, or null.
• Documents up to 10 MB; no OCR, so scanned PDFs are not supported.
• Charged per document delivered (current prices are on the Pricing tab); documents that fail, are too big, scanned, damaged or not allowed by robots.txt are free.

More: Document to Markdown on frameskim.dev

What you get

{
  "url": "https://example.com/report.pdf",
  "type": "pdf",
  "title": "Annual Report",
  "markdown": "# Annual Report\n\n...",
  "truncated": false
}

• type is pdf, docx, pptx or xlsx; title is the document's own title, or null.
• truncated is true when the markdown passed 500,000 characters and was cut.
• A document that could not be delivered has error instead of markdown, with the reason, and is not charged.
• The run's status message says how many documents were delivered and failed, and why the run stopped early, if it did.
• If nothing is delivered, the run still ends as succeeded: each document that failed is in the dataset with its error, the status message gives the first reason, and nothing was charged.

Input

Field	What it does
urls	From 1 to 50 URLs of PDF, DOCX, PPTX or XLSX files. A repeated URL is read once.

Limits

• 10 MB per document, 30 s per download attempt and 120 s to convert it. A download that runs out of time, cannot connect or gets a server error is tried once more on a new connection; if that fails too, the document fails and is not charged.
• One document at a time, so a run of 50 large documents can reach its time limit; the documents done by then are delivered and charged, and the message says why it stopped.
• Set a maximum charge per run to cap spending: the run stops before a document that would pass it.

Not affiliated with Microsoft; Word, PowerPoint and Excel are trademarks of Microsoft Corporation, named here only for the file formats this actor reads.

Support

Every error says what was wrong. For anything else, see https://frameskim.dev/terms.

Terms and privacy

Document to Markdown for AI Agents is operated by Emttn LLC and is not affiliated with, endorsed by or sponsored by the sites whose documents it reads. You need a lawful basis to fetch, copy and use each document you list, and you are responsible for following each document's license, its site's terms, copyright and privacy law; a public document or a robots.txt allow is not a license to its content. The markdown is an automatic extraction and may be incomplete or inaccurate. Terms: https://frameskim.dev/terms. Privacy: https://frameskim.dev/privacy. Questions: support@frameskim.dev.